| { | |
| "best_metric": 0.8695652173913043, | |
| "best_model_checkpoint": "vit-base-patch16-224-ve-U13-b-80\\checkpoint-357", | |
| "epoch": 73.84615384615384, | |
| "eval_steps": 500, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.3847672939300537, | |
| "eval_runtime": 0.8177, | |
| "eval_samples_per_second": 56.258, | |
| "eval_steps_per_second": 2.446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 1.3848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.369154930114746, | |
| "eval_runtime": 0.8317, | |
| "eval_samples_per_second": 55.306, | |
| "eval_steps_per_second": 2.405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.3184399604797363, | |
| "eval_runtime": 0.811, | |
| "eval_samples_per_second": 56.718, | |
| "eval_steps_per_second": 2.466, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2217472791671753, | |
| "eval_runtime": 0.8076, | |
| "eval_samples_per_second": 56.958, | |
| "eval_steps_per_second": 2.476, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 5.4276315789473686e-05, | |
| "loss": 1.2316, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.1417979001998901, | |
| "eval_runtime": 0.8299, | |
| "eval_samples_per_second": 55.427, | |
| "eval_steps_per_second": 2.41, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.0688562393188477, | |
| "eval_runtime": 0.8061, | |
| "eval_samples_per_second": 57.067, | |
| "eval_steps_per_second": 2.481, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 5.3070175438596496e-05, | |
| "loss": 1.0849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.9931420683860779, | |
| "eval_runtime": 0.8005, | |
| "eval_samples_per_second": 57.467, | |
| "eval_steps_per_second": 2.499, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 5.18640350877193e-05, | |
| "loss": 0.9314, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9457834362983704, | |
| "eval_runtime": 0.8262, | |
| "eval_samples_per_second": 55.679, | |
| "eval_steps_per_second": 2.421, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8674918413162231, | |
| "eval_runtime": 0.8035, | |
| "eval_samples_per_second": 57.252, | |
| "eval_steps_per_second": 2.489, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 5.0657894736842104e-05, | |
| "loss": 0.8001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8148000240325928, | |
| "eval_runtime": 0.7969, | |
| "eval_samples_per_second": 57.726, | |
| "eval_steps_per_second": 2.51, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.9451754385964915e-05, | |
| "loss": 0.6493, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.769162118434906, | |
| "eval_runtime": 0.8005, | |
| "eval_samples_per_second": 57.466, | |
| "eval_steps_per_second": 2.499, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6428003311157227, | |
| "eval_runtime": 0.822, | |
| "eval_samples_per_second": 55.964, | |
| "eval_steps_per_second": 2.433, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.5145, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6024693250656128, | |
| "eval_runtime": 0.8162, | |
| "eval_samples_per_second": 56.361, | |
| "eval_steps_per_second": 2.45, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.703947368421053e-05, | |
| "loss": 0.379, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.5621142387390137, | |
| "eval_runtime": 0.8058, | |
| "eval_samples_per_second": 57.084, | |
| "eval_steps_per_second": 2.482, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5298471450805664, | |
| "eval_runtime": 0.8003, | |
| "eval_samples_per_second": 57.479, | |
| "eval_steps_per_second": 2.499, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.2942, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.5791422128677368, | |
| "eval_runtime": 0.8077, | |
| "eval_samples_per_second": 56.953, | |
| "eval_steps_per_second": 2.476, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.462719298245614e-05, | |
| "loss": 0.2096, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.5814288854598999, | |
| "eval_runtime": 0.8643, | |
| "eval_samples_per_second": 53.224, | |
| "eval_steps_per_second": 2.314, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7828608751296997, | |
| "eval_runtime": 0.8165, | |
| "eval_samples_per_second": 56.341, | |
| "eval_steps_per_second": 2.45, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 0.2113, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5657770037651062, | |
| "eval_runtime": 0.8565, | |
| "eval_samples_per_second": 53.708, | |
| "eval_steps_per_second": 2.335, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.221491228070176e-05, | |
| "loss": 0.2143, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7036240696907043, | |
| "eval_runtime": 0.8255, | |
| "eval_samples_per_second": 55.723, | |
| "eval_steps_per_second": 2.423, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.5923811197280884, | |
| "eval_runtime": 0.8302, | |
| "eval_samples_per_second": 55.408, | |
| "eval_steps_per_second": 2.409, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 4.100877192982456e-05, | |
| "loss": 0.1752, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6851876974105835, | |
| "eval_runtime": 0.8226, | |
| "eval_samples_per_second": 55.919, | |
| "eval_steps_per_second": 2.431, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7237065434455872, | |
| "eval_runtime": 0.7855, | |
| "eval_samples_per_second": 58.561, | |
| "eval_steps_per_second": 2.546, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.9802631578947374e-05, | |
| "loss": 0.1238, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.674297571182251, | |
| "eval_runtime": 0.8164, | |
| "eval_samples_per_second": 56.342, | |
| "eval_steps_per_second": 2.45, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.1401, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8462918996810913, | |
| "eval_runtime": 0.8553, | |
| "eval_samples_per_second": 53.782, | |
| "eval_steps_per_second": 2.338, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7871569991111755, | |
| "eval_runtime": 0.8495, | |
| "eval_samples_per_second": 54.151, | |
| "eval_steps_per_second": 2.354, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.739035087719298e-05, | |
| "loss": 0.1544, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5491929054260254, | |
| "eval_runtime": 0.8006, | |
| "eval_samples_per_second": 57.46, | |
| "eval_steps_per_second": 2.498, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.618421052631579e-05, | |
| "loss": 0.1163, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.5755753517150879, | |
| "eval_runtime": 0.7952, | |
| "eval_samples_per_second": 57.85, | |
| "eval_steps_per_second": 2.515, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7621129751205444, | |
| "eval_runtime": 0.8004, | |
| "eval_samples_per_second": 57.473, | |
| "eval_steps_per_second": 2.499, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.49780701754386e-05, | |
| "loss": 0.1121, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6971735954284668, | |
| "eval_runtime": 0.8533, | |
| "eval_samples_per_second": 53.91, | |
| "eval_steps_per_second": 2.344, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.377192982456141e-05, | |
| "loss": 0.1065, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5722712874412537, | |
| "eval_runtime": 0.8172, | |
| "eval_samples_per_second": 56.291, | |
| "eval_steps_per_second": 2.447, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7502769231796265, | |
| "eval_runtime": 0.82, | |
| "eval_samples_per_second": 56.099, | |
| "eval_steps_per_second": 2.439, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.256578947368421e-05, | |
| "loss": 0.1021, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6127011775970459, | |
| "eval_runtime": 0.8337, | |
| "eval_samples_per_second": 55.178, | |
| "eval_steps_per_second": 2.399, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.1359649122807015e-05, | |
| "loss": 0.1048, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5733683109283447, | |
| "eval_runtime": 0.8175, | |
| "eval_samples_per_second": 56.266, | |
| "eval_steps_per_second": 2.446, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5817247033119202, | |
| "eval_runtime": 0.7923, | |
| "eval_samples_per_second": 58.058, | |
| "eval_steps_per_second": 2.524, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 3.0153508771929826e-05, | |
| "loss": 0.0848, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5902915000915527, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 56.47, | |
| "eval_steps_per_second": 2.455, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.894736842105263e-05, | |
| "loss": 0.0769, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7073713541030884, | |
| "eval_runtime": 0.8284, | |
| "eval_samples_per_second": 55.526, | |
| "eval_steps_per_second": 2.414, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5835453271865845, | |
| "eval_runtime": 0.8538, | |
| "eval_samples_per_second": 53.878, | |
| "eval_steps_per_second": 2.343, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.774122807017544e-05, | |
| "loss": 0.0825, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6373018622398376, | |
| "eval_runtime": 0.8412, | |
| "eval_samples_per_second": 54.687, | |
| "eval_steps_per_second": 2.378, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.6535087719298248e-05, | |
| "loss": 0.0676, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6793442368507385, | |
| "eval_runtime": 0.7973, | |
| "eval_samples_per_second": 57.693, | |
| "eval_steps_per_second": 2.508, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6555591225624084, | |
| "eval_runtime": 0.8468, | |
| "eval_samples_per_second": 54.321, | |
| "eval_steps_per_second": 2.362, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.5328947368421052e-05, | |
| "loss": 0.0703, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.632850170135498, | |
| "eval_runtime": 0.8121, | |
| "eval_samples_per_second": 56.646, | |
| "eval_steps_per_second": 2.463, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.68681401014328, | |
| "eval_runtime": 0.8165, | |
| "eval_samples_per_second": 56.337, | |
| "eval_steps_per_second": 2.449, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.412280701754386e-05, | |
| "loss": 0.0574, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.5996745824813843, | |
| "eval_runtime": 0.7976, | |
| "eval_samples_per_second": 57.67, | |
| "eval_steps_per_second": 2.507, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.0523, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5846443176269531, | |
| "eval_runtime": 0.8488, | |
| "eval_samples_per_second": 54.192, | |
| "eval_steps_per_second": 2.356, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.721405029296875, | |
| "eval_runtime": 0.8605, | |
| "eval_samples_per_second": 53.459, | |
| "eval_steps_per_second": 2.324, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.1710526315789474e-05, | |
| "loss": 0.064, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5229998230934143, | |
| "eval_runtime": 0.8295, | |
| "eval_samples_per_second": 55.454, | |
| "eval_steps_per_second": 2.411, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 2.050438596491228e-05, | |
| "loss": 0.082, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5849720239639282, | |
| "eval_runtime": 0.8195, | |
| "eval_samples_per_second": 56.134, | |
| "eval_steps_per_second": 2.441, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.634585976600647, | |
| "eval_runtime": 0.8166, | |
| "eval_samples_per_second": 56.328, | |
| "eval_steps_per_second": 2.449, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.0694, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6389460563659668, | |
| "eval_runtime": 0.806, | |
| "eval_samples_per_second": 57.075, | |
| "eval_steps_per_second": 2.482, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.8092105263157896e-05, | |
| "loss": 0.0462, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5813049077987671, | |
| "eval_runtime": 0.8224, | |
| "eval_samples_per_second": 55.932, | |
| "eval_steps_per_second": 2.432, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.5792219042778015, | |
| "eval_runtime": 0.791, | |
| "eval_samples_per_second": 58.152, | |
| "eval_steps_per_second": 2.528, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6885964912280704e-05, | |
| "loss": 0.044, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5723995566368103, | |
| "eval_runtime": 0.8166, | |
| "eval_samples_per_second": 56.33, | |
| "eval_steps_per_second": 2.449, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5679824561403508e-05, | |
| "loss": 0.0538, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6293544769287109, | |
| "eval_runtime": 0.8204, | |
| "eval_samples_per_second": 56.069, | |
| "eval_steps_per_second": 2.438, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.8695652173913043, | |
| "eval_loss": 0.5741947889328003, | |
| "eval_runtime": 0.8245, | |
| "eval_samples_per_second": 55.794, | |
| "eval_steps_per_second": 2.426, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.4473684210526315e-05, | |
| "loss": 0.0455, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.695148229598999, | |
| "eval_runtime": 0.7996, | |
| "eval_samples_per_second": 57.526, | |
| "eval_steps_per_second": 2.501, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.3267543859649124e-05, | |
| "loss": 0.0537, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6457701325416565, | |
| "eval_runtime": 0.817, | |
| "eval_samples_per_second": 56.302, | |
| "eval_steps_per_second": 2.448, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6258807182312012, | |
| "eval_runtime": 0.839, | |
| "eval_samples_per_second": 54.83, | |
| "eval_steps_per_second": 2.384, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.206140350877193e-05, | |
| "loss": 0.038, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6748208403587341, | |
| "eval_runtime": 0.8591, | |
| "eval_samples_per_second": 53.545, | |
| "eval_steps_per_second": 2.328, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0855263157894737e-05, | |
| "loss": 0.039, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7235903739929199, | |
| "eval_runtime": 0.817, | |
| "eval_samples_per_second": 56.301, | |
| "eval_steps_per_second": 2.448, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.775827169418335, | |
| "eval_runtime": 0.7981, | |
| "eval_samples_per_second": 57.64, | |
| "eval_steps_per_second": 2.506, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.0304, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7253482937812805, | |
| "eval_runtime": 0.8039, | |
| "eval_samples_per_second": 57.22, | |
| "eval_steps_per_second": 2.488, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7512924075126648, | |
| "eval_runtime": 0.7986, | |
| "eval_samples_per_second": 57.602, | |
| "eval_steps_per_second": 2.504, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.442982456140352e-06, | |
| "loss": 0.051, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7546844482421875, | |
| "eval_runtime": 0.8159, | |
| "eval_samples_per_second": 56.378, | |
| "eval_steps_per_second": 2.451, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 7.2368421052631575e-06, | |
| "loss": 0.0355, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8115072846412659, | |
| "eval_runtime": 0.9032, | |
| "eval_samples_per_second": 50.928, | |
| "eval_steps_per_second": 2.214, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7768033742904663, | |
| "eval_runtime": 0.8047, | |
| "eval_samples_per_second": 57.165, | |
| "eval_steps_per_second": 2.485, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 6.030701754385965e-06, | |
| "loss": 0.0435, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7829141020774841, | |
| "eval_runtime": 0.847, | |
| "eval_samples_per_second": 54.308, | |
| "eval_steps_per_second": 2.361, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.824561403508772e-06, | |
| "loss": 0.0313, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7786911129951477, | |
| "eval_runtime": 0.8096, | |
| "eval_samples_per_second": 56.815, | |
| "eval_steps_per_second": 2.47, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7720622420310974, | |
| "eval_runtime": 0.7835, | |
| "eval_samples_per_second": 58.708, | |
| "eval_steps_per_second": 2.553, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.6184210526315788e-06, | |
| "loss": 0.0378, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7671762704849243, | |
| "eval_runtime": 0.8076, | |
| "eval_samples_per_second": 56.962, | |
| "eval_steps_per_second": 2.477, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.412280701754386e-06, | |
| "loss": 0.0339, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.763389527797699, | |
| "eval_runtime": 0.8002, | |
| "eval_samples_per_second": 57.483, | |
| "eval_steps_per_second": 2.499, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7615298628807068, | |
| "eval_runtime": 0.7982, | |
| "eval_samples_per_second": 57.632, | |
| "eval_steps_per_second": 2.506, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.206140350877193e-06, | |
| "loss": 0.0311, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7604991793632507, | |
| "eval_runtime": 0.8004, | |
| "eval_samples_per_second": 57.47, | |
| "eval_steps_per_second": 2.499, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0302, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7603499293327332, | |
| "eval_runtime": 0.7863, | |
| "eval_samples_per_second": 58.503, | |
| "eval_steps_per_second": 2.544, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 4.687651970153865e+18, | |
| "train_loss": 0.24467987176030875, | |
| "train_runtime": 1043.0523, | |
| "train_samples_per_second": 62.816, | |
| "train_steps_per_second": 0.46 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 4.687651970153865e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |